Papers by Paul Roit
Asking It All: Generating Contextualized Questions for any Semantic Role (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to question generation require conditioning on existing answers in text . previous work required human-curated templates, limiting coverage and question fluency . |
| Approach: | They propose a task of role question generation that produces a prototype and revises it to be contextually appropriate for the passage. |
| Outcome: | The proposed model generates diverse and well-formed questions for a large, broad-coverage ontology of predicates and roles. |
LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models (2022.emnlp-demos)
Copied to clipboard
| Challenge: | Transformer-based language models (LMs) are opaque and unexplained, causing problems for endusers and developers who wish to debug or fix their behaviour. |
| Approach: | They propose an interactive debugger tool for transformer-based LMs that provides a fine-grained interpretation of the model's internal prediction process and a powerful framework for intervening in LM behavior. |
| Outcome: | The proposed tool provides a fine-grained interpretation of the model's internal prediction construction process, and a powerful framework for intervening in LM behavior. |
Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback (2023.acl-long)
Copied to clipboard
Paul Roit, Johan Ferret, Lior Shani, Roee Aharoni, Geoffrey Cideron, Robert Dadashi, Matthieu Geist, Sertan Girgin, Leonard Hussenot, Orgad Keller, Nikola Momchev, Sabela Ramos Garea, Piotr Stanczyk, Nino Vieillard, Olivier Bachem, Gal Elidan, Avinatan Hassidim, Olivier Pietquin, Idan Szpektor
| Challenge: | Recent advances in abstractive summarization systems produce factually inconsistent text . this is emphasized in tasks like summarizing, which often produce inconsistent text with no input article . |
| Approach: | They use reinforcement learning to optimize for factual consistency and explore trade-offs . they use textual-entailment rewards to optimize the accuracy of the generated summaries . |
| Outcome: | The proposed method improves faithfulness, salience and conciseness of the generated summaries. |
QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to consolidate textual inputs are difficult to implement . a recent study aims to capture content overlap by combining multiple textual elements . |
| Approach: | They propose to align predicate-argument relations across texts to represent content overlap . their setting exploits QA-SRL, utilizing question-answer pairs to capture predicates . |
| Outcome: | The proposed task captures content overlap beyond lexical similarity and complements cross-document coreference with proposition-level links, offering potential use for downstream tasks. |
Controlled Text Reduction (2022.emnlp-main)
Copied to clipboard
| Challenge: | Abstractive text summarization models separate the salience detection phase from the text generation phase. |
| Approach: | They propose to formalize Controlled Text Reduction as a standalone task . they advocate the potential of such models for modular fully-automatic summarization . |
| Outcome: | The proposed model shows that it is possible to produce a reduced version of a source text using decomposed modeling. |
Extending Multi-Text Sentence Fusion Resources via Pyramid Annotations (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing datasets for sentence fusion tasks are limited in size and scope . despite recent advances, cross-document tasks such as multi-document summarization have not progressed with the same pace. |
| Approach: | They propose to extend a sentence fusion dataset by almost four times its original size . they relabel the dataset and employ more data sources to improve model performance . |
| Outcome: | The proposed dataset triples the size of an earlier dataset and improves performance . it also includes more complex training instances better reflecting those found in "the wild" |
Controlled Crowdsourcing for High-Quality QA-SRL Annotation (2020.acl-main)
Copied to clipboard
Paul Roit, Ayal Klein, Daniela Stepanov, Jonathan Mamou, Julian Michael, Gabriel Stanovsky, Luke Zettlemoyer, Ido Dagan
| Challenge: | Question-answer driven Semantic Role Labeling (QA-SRL) is an open and natural flavour of SRL, potentially attainable from laymen. |
| Approach: | They propose a question-answer driven semantic role labeling approach that uses question-announced questions to label predicate-argument relationships. |
| Outcome: | The proposed method yields high-quality annotation with dramatically higher coverage, enabling future replicable research of natural semantic annotations. |
Localizing Factual Inconsistencies in Attributable Text Generation (2026.tacl-1)
Copied to clipboard
Arie Cattan, Paul Roit, Shiyue Zhang, David Wan, Roee Aharoni, Idan Szpektor, Mohit Bansal, Ido Dagan
| Challenge: | Existing methods for detecting hallucinations in model-generated texts fail to pinpoint errors. |
| Approach: | They propose a formalism for localizing factual inconsistencies in attributable text generation . they propose to decompose the generated text into simple question-answer pairs . |
| Outcome: | The proposed method achieves substantial inter-annotator agreement while achieving a substantial consistency score. |